Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12846
    Prev
    Next
    INDEX
    Explanations

    expressions indicating agreement or alignment between different statements or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.68
     anhydrous
    -0.60
    .*")]
    -0.60
    DockStyle
    -0.60
     initComponents
    -0.60
    حياته
    -0.58
     BorderSide
    -0.56
    Sucesor
    -0.56
    ieteur
    -0.54
    Hauptartikel
    -0.54
    POSITIVE LOGITS
     matches
    0.96
     match
    0.94
     congruent
    0.91
     matching
    0.88
     matched
    0.85
     coincide
    0.85
     соответствует
    0.83
     overeen
    0.83
     MATCH
    0.83
     conforme
    0.82
    Activations Density 0.465%

    No Known Activations